Data Mining Research Project Report Generating Texts in Estonian Language. Author: Robert Roosalu Supervisor: Tambet Matiisen
|
|
- Eleanore Bridges
- 5 years ago
- Views:
Transcription
1 Data Mining Research Project Report Generating Texts in Estonian Language Author: Robert Roosalu Supervisor: Tambet Matiisen Tartu University Institute of Computer Science January 2016
2 Introduction The aim of this project is to replicate the results of Andrej Karpathy's blog post [1]. In it he demonstrates training a recurrent neural network to generate text character by character. The post shows examples of English text, Wikipedia markup, LaTeX markup and even C++ source code. An implementation of the described model can be found in the deep learning library Keras's example set. The goal of this project is to use it on an Estonian dataset and to explore the model's hyperparameter space. This project should provide insight into: * how different hyperparameters effect the performance of the model * comparing the quality of generated text * differences when training on Estonian versus training on English datasets Background The concept of using RNNs for character by character prediction was first demonstrated by Ilya Sutskever et al in 2011 [2]. Besides the fun application of generating text, they describe how such models could be used in text compression. They compare the RNN solution to two previous state of the art methods, while achieving competetive results: * Memoizer a hierarchical Bayesian model * PAQ a data compression method, that uses probabilistic sampling. The sampling is done by a mixture of context-models (n-gram, whole word n-gram, etc). The mixing proportions (when to prefer which model) take into consideration the current context. Dataset I began by concatenating 160 books from Estonian literature (since year 1990). They were part of the balanced corpus, provided by Tartu University computational linguistics group. [3] The books were in the TEI format (uses XML syntax), requiring some parsing to get the pure text format I was after. The resulting 35 MB dataset took too long to process. I estimated a reasonable size to allow me get results would be around 1 MB, as that got interpretable results in half a day intervals. I split the original concatenated dataset from the 1 MB marker, and ended up with Rein Põder's Hiliskevad and a quarter of Ene Mihkelson's Ahasveeruse Uni.
3 Method The architecture presented in both Karpathy's post and the Keras example set: 2-layer LSTM, 512 neurons Dropoout 0.2 Softmax activation Categorical Crossentropy loss RMSProp For hyperparameter tuning, this is the set I tweaked, with their baseline values: neurons, 512 dropout, 0.2 corpus_size, 1M window_size, 20 batch_size, 256 epoch_number, 1 window_size is the substring size of the training examples. epoch_number is a parameter for the fitting function. Training in the original code is done in iterations, after each an example sample was produced. The epoch_number is a parameter for the fit function. At first glance it seemed to have a different effect then the iterations, but as expected, they turned out to be the same thing. When conducting these experiments, it didn't make sense to me to use a validation set, as this problem seems a bit different from regular machine learning tasks. However, as described by Sutskever in [2], it would make sense. Instead, I used a custom metric to accompany the training loss, described by eq 1. (1) We can affect the sampling of the text with a temperature parameter. Lower temperature means picking characters that are most probable according to the model. The idea is, that models predicting correct words even at high temperatures, should be good. For the experiment I tried various different hyperparameter values. I recorded the loss and the custom accuracy after each iteration.
4 Results I obtained results from 14 different models. The models were trained for varying lengths of time, between a day and two days. All the trained models' cost functions are presented in figure 1. Figure 1. Cost functions of all the experiments. The longest, light blue line is the baseline, with default hyperparameter values. Figure 2. Loss functions for modified batch, corpus, window_size and dropout.
5 Figure 2 displays cost functions for varying batch, corpus, window sizes, and droput. Larger batch sizes were hindering, but it seemed a smaller batch size would make it better. Larger corpus did not improve the loss for a day of training. It could be the network is too small. Or it could take longer to achieve the same loss value, due to more input data. Larger window seems to have no effect. The network seems to care about character history of only up to 20. Larger dropout values worsen the loss. Unfortunately a smaller run on dropout of 0.1 got lost. Varying the fitting functions's epoch number seemed to have a positive effect, until I realised it's essentially the same thing iteratively running the fitting. Figure 3. Fitting with higher epoch number on the left, normalised to iterations on the right. The strangest loss function was produced by one larger network, as presented in figure 4. Figure 4. Modifying the network layer size.
6 To see how the larger network compares to the baseline, I plot them both against the accuracy metric described in he previous section. Figure 5. Comparison of networks sized 512 and 1024 with the accuracy metric. The low temperature sample goes to nearly 100% in the beginning, due to generating only short, correct words. It's interesting, how the low and high temperature generated sample accuracies converge. Perhaps convergence would indicate that training is done. The bigger network displays quicker convergence and also a slightly higher accuracy on the high temperature samples. This would indicate a better model. However, reading through the generated texts, at around iteration 60, the smaller network seemed to make more sense. Some examples of generated text: 512 neurons: Low temp: mees oli ta vastanud, et ta oli ka enam mingit neist temasse viinalt parjada sellele peale mõneda kohale ja arusaatust taastasse saati. ja see kasvab veel tema pea sees. nii et ma teadsin, et mulle tundus mulle ka enam midagi ja ette vastama. ma ei ole kui tema keegi meele. High temp: kinni üle metsavendi tema silmis peaaegu palamamaatlus. ainult ette vaaduks tõgima!, viga minu omida... esimesel tegul. meil oli ruttanud, päris kilduv paesa vananud ja just naguti olemuspoolt ühne sedasama vajaks neurons: Low temp: kuid midagi ses maastikus, mis on see võimalik. ja millal ma seda kõrvale ja kuulus see tahtis mind ema taastaks, kui mu kümmeks säärasega jooksid rõhkumise haamatust küünalda letk High temp: ma olin karini armendama näonud paidagi elanud. selgus, et veel siis naiselik. tegelikult oli hetke teeline piri, oli ma auendaid kordi alla peen, seda tuli ta rihumad loodus.
7 Discussion Tuning the parameters mostly did not lead to a notable increase in either training loss, measured accuracy, or perceived text quality. The dataset I ended up using, was in the same size range, as the one used in the original example. The author of which had probably done a good job tuning the parameters already. The original text was in English, and the samples from it made much more sense, then the ones generated on Estonian. This indicates how Estonian language has a more complicated structure, to be captured with such a model. The main take away for me, was learning to set up such an experiment. This time it was a bit error prone, concluding in some lost measurements. Logging the results should be as automatic as possible, with minimum amount of manual work. The latter of which makes the process a bit tedious and also greatly increases the chance of mistakes. Future work There are some loose ends in this work, such as measuring smaller batch sizes, and seeing how the bigger network behaves after longer training. However, it was proved that the dataset is too small to obtain any reasonable results. So the first thing would be to increase the dataset greatly, and rerun the hyperparameter tuning process. Following experiments should include the validation loss as well. Furthermore, it would be interesting to try different accuracy metrics, for example measuring the amount of distinct words in the samples, or checking how much of the sampled text is present in the original data. This would help gauge the models originality. Conclusion This research project in data mining set out to try the recurrent neural network model presented by Andrej Karpathy [1], originally by Ilya Sutskever et al [2], for generating Estonian text. An implementation of which was included in the Keras's example set worked quite well, so I set out to explore it's hyperparameters. The available timeframe set a limit on the dataset size, which coincided with the size of the examples's dataset. Hyperparameter search revealed, how the original hyperparameters were good enough. A metric for measuring the models's performance was used, which observed the amount of correct words in the generated sample. This helps to automatically estimate the goodness of a model. Comparing with the results from the example, which used English text as input, it can be said Estonian language has a more complex structure. Future work should build on the fact, that 1 MB of data is too small for this kind of sampling.
8 References [1] [2] I. Sutskever, J. Martens, G. Hinton. Generating Text with Recurrent Neural Networks. In Proceedings of the 28th International Conference on Machine Learning, [3]
arxiv: v1 [stat.ml] 23 Jan 2017
Learning what to look in chest X-rays with a recurrent visual attention model arxiv:1701.06452v1 [stat.ml] 23 Jan 2017 Petros-Pavlos Ypsilantis Department of Biomedical Engineering King s College London
More informationA HMM-based Pre-training Approach for Sequential Data
A HMM-based Pre-training Approach for Sequential Data Luca Pasa 1, Alberto Testolin 2, Alessandro Sperduti 1 1- Department of Mathematics 2- Department of Developmental Psychology and Socialisation University
More informationRetinopathy Net. Alberto Benavides Robert Dadashi Neel Vadoothker
Retinopathy Net Alberto Benavides Robert Dadashi Neel Vadoothker Motivation We were interested in applying deep learning techniques to the field of medical imaging Field holds a lot of promise and can
More informationObject Detectors Emerge in Deep Scene CNNs
Object Detectors Emerge in Deep Scene CNNs Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba Presented By: Collin McCarthy Goal: Understand how objects are represented in CNNs Are
More informationConvolutional and LSTM Neural Networks
Convolutional and LSTM Neural Networks Vanessa Jurtz January 12, 2016 Contents Neural networks and GPUs Lasagne Peptide binding to MHC class II molecules Convolutional Neural Networks (CNN) Recurrent and
More informationUsing Deep Convolutional Networks for Gesture Recognition in American Sign Language
Using Deep Convolutional Networks for Gesture Recognition in American Sign Language Abstract In the realm of multimodal communication, sign language is, and continues to be, one of the most understudied
More informationDeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation
DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation Biyi Fang Michigan State University ACM SenSys 17 Nov 6 th, 2017 Biyi Fang (MSU) Jillian Co (MSU) Mi Zhang
More informationConvolutional Neural Networks for Text Classification
Convolutional Neural Networks for Text Classification Sebastian Sierra MindLab Research Group July 1, 2016 ebastian Sierra (MindLab Research Group) NLP Summer Class July 1, 2016 1 / 32 Outline 1 What is
More informationCSE Introduction to High-Perfomance Deep Learning ImageNet & VGG. Jihyung Kil
CSE 5194.01 - Introduction to High-Perfomance Deep Learning ImageNet & VGG Jihyung Kil ImageNet Classification with Deep Convolutional Neural Networks Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton,
More informationarxiv: v1 [cs.lg] 6 Oct 2016
Combining Generative and Discriminative Neural Networks for Sleep Stages Classification Endang Purnama Giri 1,2, Mohamad Ivan Fanany 1, Aniati Murni Arymurthy 1, arxiv:1610.01741v1 [cs.lg] 6 Oct 2016 1
More informationAutomatic Context-Aware Image Captioning
Technical Disclosure Commons Defensive Publications Series May 23, 2017 Automatic Context-Aware Image Captioning Sandro Feuz Sebastian Millius Follow this and additional works at: http://www.tdcommons.org/dpubs_series
More informationSmaller, faster, deeper: University of Edinburgh MT submittion to WMT 2017
Smaller, faster, deeper: University of Edinburgh MT submittion to WMT 2017 Rico Sennrich, Alexandra Birch, Anna Currey, Ulrich Germann, Barry Haddow, Kenneth Heafield, Antonio Valerio Miceli Barone, Philip
More informationConvolutional and LSTM Neural Networks
Convolutional and LSTM Neural Networks Vanessa Jurtz January 11, 2017 Contents Neural networks and GPUs Lasagne Peptide binding to MHC class II molecules Convolutional Neural Networks (CNN) Recurrent and
More informationFactoid Question Answering
Factoid Question Answering CS 898 Project June 12, 2017 Salman Mohammed David R. Cheriton School of Computer Science University of Waterloo Motivation Source: https://www.apple.com/newsroom/2017/01/hey-siri-whos-going-to-win-the-super-bowl/
More informationImage Classification with TensorFlow: Radiomics 1p/19q Chromosome Status Classification Using Deep Learning
Image Classification with TensorFlow: Radiomics 1p/19q Chromosome Status Classification Using Deep Learning Charles Killam, LP.D. Certified Instructor, NVIDIA Deep Learning Institute NVIDIA Corporation
More informationPractical Bayesian Optimization of Machine Learning Algorithms. Jasper Snoek, Ryan Adams, Hugo LaRochelle NIPS 2012
Practical Bayesian Optimization of Machine Learning Algorithms Jasper Snoek, Ryan Adams, Hugo LaRochelle NIPS 2012 ... (Gaussian Processes) are inadequate for doing speech and vision. I still think they're
More informationSkin cancer reorganization and classification with deep neural network
Skin cancer reorganization and classification with deep neural network Hao Chang 1 1. Department of Genetics, Yale University School of Medicine 2. Email: changhao86@gmail.com Abstract As one kind of skin
More informationSawtooth Software. MaxDiff Analysis: Simple Counting, Individual-Level Logit, and HB RESEARCH PAPER SERIES. Bryan Orme, Sawtooth Software, Inc.
Sawtooth Software RESEARCH PAPER SERIES MaxDiff Analysis: Simple Counting, Individual-Level Logit, and HB Bryan Orme, Sawtooth Software, Inc. Copyright 009, Sawtooth Software, Inc. 530 W. Fir St. Sequim,
More informationDeep CNNs for Diabetic Retinopathy Detection
Deep CNNs for Diabetic Retinopathy Detection Alex Tamkin Stanford University atamkin@stanford.edu Iain Usiri Stanford University iusiri@stanford.edu Chala Fufa Stanford University cfufa@stanford.edu 1
More informationImage Captioning using Reinforcement Learning. Presentation by: Samarth Gupta
Image Captioning using Reinforcement Learning Presentation by: Samarth Gupta 1 Introduction Summary Supervised Models Image captioning as RL problem Actor Critic Architecture Policy Gradient architecture
More informationInferring Clinical Correlations from EEG Reports with Deep Neural Learning
Inferring Clinical Correlations from EEG Reports with Deep Neural Learning Methods for Identification, Classification, and Association using EHR Data S23 Travis R. Goodwin (Presenter) & Sanda M. Harabagiu
More informationClinical Trials: Non-Muscle Invasive Bladder Cancer. Tuesday, May 17th, Part II
Clinical Trials: Non-Muscle Invasive Bladder Cancer Tuesday, May 17th, 2016 Part II Presented by Yair Lotan, MD is holder of the Helen J. and Robert S. Strauss Professorship in Urology and Chief of Urologic
More informationarxiv: v1 [cs.ai] 28 Nov 2017
: a better way of the parameters of a Deep Neural Network arxiv:1711.10177v1 [cs.ai] 28 Nov 2017 Guglielmo Montone Laboratoire Psychologie de la Perception Université Paris Descartes, Paris montone.guglielmo@gmail.com
More informationQuality Improvement of Causes of Death Statistics by Automated Coding in Estonia, 2011
Quality Improvement of Causes of Death Statistics by Automated Coding in Estonia, 2011 Technical Implementation report, Grant agreement nr 10501.2009.002-2009.461 Introduction The grant agreement between
More informationAutomated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images
Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images Tae Joon Jun, Dohyeun Kim, and Daeyoung Kim School of Computing, KAIST,
More informationMinimum Risk Training For Neural Machine Translation. Shiqi Shen, Yong Cheng, Zhongjun He, Wei He, Hua Wu, Maosong Sun, and Yang Liu
Minimum Risk Training For Neural Machine Translation Shiqi Shen, Yong Cheng, Zhongjun He, Wei He, Hua Wu, Maosong Sun, and Yang Liu ACL 2016, Berlin, German, August 2016 Machine Translation MT: using computer
More informationHOW AI WILL IMPACT SUBTITLE PRODUCTION
HOW AI WILL IMPACT SUBTITLE PRODUCTION 1 WHAT IS AI IN A BROADCAST CONTEXT? 2 What is AI in a Broadcast Context? I m sorry, Dave. I m afraid I can t do that. Image By Cryteria [CC BY 3.0 (https://creativecommons.org/licenses/by/3.0)],
More informationExpert System Profile
Expert System Profile GENERAL Domain: Medical Main General Function: Diagnosis System Name: INTERNIST-I/ CADUCEUS (or INTERNIST-II) Dates: 1970 s 1980 s Researchers: Ph.D. Harry Pople, M.D. Jack D. Myers
More informationDilated Recurrent Neural Network for Short-Time Prediction of Glucose Concentration
Dilated Recurrent Neural Network for Short-Time Prediction of Glucose Concentration Jianwei Chen, Kezhi Li, Pau Herrero, Taiyu Zhu, Pantelis Georgiou Department of Electronic and Electrical Engineering,
More informationLOOK, LISTEN, AND DECODE: MULTIMODAL SPEECH RECOGNITION WITH IMAGES. Felix Sun, David Harwath, and James Glass
LOOK, LISTEN, AND DECODE: MULTIMODAL SPEECH RECOGNITION WITH IMAGES Felix Sun, David Harwath, and James Glass MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA {felixsun,
More informationTraining deep Autoencoders for collaborative filtering Oleksii Kuchaiev & Boris Ginsburg
Training deep Autoencoders for collaborative filtering Oleksii Kuchaiev & Boris Ginsburg Motivation Personalized recommendations 2 Key points (spoiler alert) 1. Deep autoencoder for collaborative filtering
More informationarxiv: v1 [cs.lg] 4 Feb 2019
Machine Learning for Seizure Type Classification: Setting the benchmark Subhrajit Roy [000 0002 6072 5500], Umar Asif [0000 0001 5209 7084], Jianbin Tang [0000 0001 5440 0796], and Stefan Harrer [0000
More informationUnsupervised Measurement of Translation Quality Using Multi-engine, Bi-directional Translation
Unsupervised Measurement of Translation Quality Using Multi-engine, Bi-directional Translation Menno van Zaanen and Simon Zwarts Division of Information and Communication Sciences Department of Computing
More informationConvolutional Neural Networks for Estimating Left Ventricular Volume
Convolutional Neural Networks for Estimating Left Ventricular Volume Ryan Silva Stanford University rdsilva@stanford.edu Maksim Korolev Stanford University mkorolev@stanford.edu Abstract End-systolic and
More informationPredicting Diabetes and Heart Disease Using Features Resulting from KMeans and GMM Clustering
Predicting Diabetes and Heart Disease Using Features Resulting from KMeans and GMM Clustering Kunal Sharma CS 4641 Machine Learning Abstract Clustering is a technique that is commonly used in unsupervised
More information[PDF] Keys To The Mind, Learn How To Hypnotize Anyone And Practice Hypnosis And Hypnotherapy Correctly
[PDF] Keys To The Mind, Learn How To Hypnotize Anyone And Practice Hypnosis And Hypnotherapy Correctly "Keys to the Mind" will teach you exactly what you need to know to become a hypnotist. Learn how to
More informationMedical Knowledge Attention Enhanced Neural Model. for Named Entity Recognition in Chinese EMR
Medical Knowledge Attention Enhanced Neural Model for Named Entity Recognition in Chinese EMR Zhichang Zhang, Yu Zhang, Tong Zhou College of Computer Science and Engineering, Northwest Normal University,
More informationThe Effect of Sensor Errors in Situated Human-Computer Dialogue
The Effect of Sensor Errors in Situated Human-Computer Dialogue Niels Schuette Dublin Institute of Technology niels.schutte @student.dit.ie John Kelleher Dublin Institute of Technology john.d.kelleher
More informationDeep Learning for Lip Reading using Audio-Visual Information for Urdu Language
Deep Learning for Lip Reading using Audio-Visual Information for Urdu Language Muhammad Faisal Information Technology University Lahore m.faisal@itu.edu.pk Abstract Human lip-reading is a challenging task.
More informationReading personality from blogs An evaluation of the ESCADA system
Reading personality from blogs An evaluation of the ESCADA system Abstract The ESCADA system is a shallow textual understanding system capable of detecting high-level patterns of affective communication.
More informationErgonomics questions will account for 13% or 26 questions of the ASP exam.
1 Ergonomics questions will account for 13% or 26 questions of the ASP exam. This lesson will help in preparing you for those questions, to include several review and sample questions for practice. 2 Carpal
More informationLearning Convolutional Neural Networks for Graphs
GA-65449 Learning Convolutional Neural Networks for Graphs Mathias Niepert Mohamed Ahmed Konstantin Kutzkov NEC Laboratories Europe Representation Learning for Graphs Telecom Safety Transportation Industry
More informationValue of emotional intelligence in veterinary practice teams
Vet Times The website for the veterinary profession https://www.vettimes.co.uk Value of emotional intelligence in veterinary practice teams Author : MAGGIE SHILCOCK Categories : Vets Date : February 17,
More informationLanguage Volunteer Guide
Language Volunteer Guide Table of Contents Introduction How You Can Make an Impact Getting Started 3 4 4 Style Guidelines Captioning Translation Review 5 7 9 10 Getting Started with Dotsub Captioning Translation
More informationEvolutionary Programming
Evolutionary Programming Searching Problem Spaces William Power April 24, 2016 1 Evolutionary Programming Can we solve problems by mi:micing the evolutionary process? Evolutionary programming is a methodology
More informationYoung Cam Jansen And The Missing Cookie Download Free (EPUB, PDF)
Young Cam Jansen And The Missing Cookie Download Free (EPUB, PDF) Cam Jansen can find a mystery anywher, even in the school lunch room! When Jason opens his lunch box and finds only cookie crumbs, Cam's
More informationMachine learning for neural decoding
Machine learning for neural decoding Joshua I. Glaser 1,2,6,7*, Raeed H. Chowdhury 3,4, Matthew G. Perich 3,4, Lee E. Miller 2-4, and Konrad P. Kording 2-7 1. Interdepartmental Neuroscience Program, Northwestern
More informationScanning Brains for Insights on Racial Perception
New York Times, Science Section, September 5, 2000 Scanning Brains for Insights on Racial Perception By DAVID BERREBY Copyright 2000 The New York Times Co. Reprinted with permission After a decade of mapping
More informationRating prediction on Amazon Fine Foods Reviews
Rating prediction on Amazon Fine Foods Reviews Chen Zheng University of California,San Diego chz022@ucsd.edu Ye Zhang University of California,San Diego yez033@ucsd.edu Yikun Huang University of California,San
More informationMachine Learning Models for Blood Glucose Level Prediction
Machine Learning Models for Blood Glucose Level Prediction Sadegh M. Hui Shen Cindy Marling Matt Wiley Franck Schwarz Nigel Struble Jay Shubrook Lijie Xia Razvan Bunescu School of EECS & Diabetes Institute,
More informationAn Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns
An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns 1. Introduction Vasily Morzhakov, Alexey Redozubov morzhakovva@gmail.com, galdrd@gmail.com Abstract Cortical
More informationA Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals
A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals Luis Guarda Bräuning (1) Nicolas Astorga (1) Enrique López Droguett (1) Marcio Moura (2) Marcelo
More informationUniversity of Cambridge Engineering Part IB Information Engineering Elective
University of Cambridge Engineering Part IB Information Engineering Elective Paper 8: Image Searching and Modelling Using Machine Learning Handout 1: Introduction to Artificial Neural Networks Roberto
More informationR Jagdeesh Kanan* et al. International Journal of Pharmacy & Technology
ISSN: 0975-766X CODEN: IJPTFI Available Online through Research Article www.ijptonline.com FACIAL EMOTION RECOGNITION USING NEURAL NETWORK Kashyap Chiranjiv Devendra, Azad Singh Tomar, Pratigyna.N.Javali,
More informationAudiovisual to Sign Language Translator
Technical Disclosure Commons Defensive Publications Series July 17, 2018 Audiovisual to Sign Language Translator Manikandan Gopalakrishnan Follow this and additional works at: https://www.tdcommons.org/dpubs_series
More informationFood Adulteration Detection Using Neural Networks. Youyang Gu
Food Adulteration Detection Using Neural Networks by Youyang Gu Submitted to the Department of Electrical Engineering and Computer Science in partial fulfillment of the requirements for the degree of Master
More informationDifferentiating Tumor and Edema in Brain Magnetic Resonance Images Using a Convolutional Neural Network
Original Article Differentiating Tumor and Edema in Brain Magnetic Resonance Images Using a Convolutional Neural Network Aida Allahverdi 1, Siavash Akbarzadeh 1, Alireza Khorrami Moghaddam 2, Armin Allahverdy
More informationThe use of Topic Modeling to Analyze Open-Ended Survey Items
The use of Topic Modeling to Analyze Open-Ended Survey Items W. Holmes Finch Maria E. Hernández Finch Constance E. McIntosh Claire Braun Ball State University Open ended survey items Researchers making
More informationFSWCHS NHS Information Packet
FSWCHS NHS Information Packet Example Student Grade: 11/Junior 26300 Airport Road, Punta Gorda Florida 33950 Home: (555)-555-5556 Cell: (the)-#is-fake Mom: Mother Student Dad: Father Student Character
More informationarxiv: v1 [cs.cv] 9 Oct 2018
Automatic Segmentation of Thoracic Aorta Segments in Low-Dose Chest CT Julia M. H. Noothout a, Bob D. de Vos a, Jelmer M. Wolterink a, Ivana Išgum a a Image Sciences Institute, University Medical Center
More informationWinograd Schema Common Sense Challenge
Winograd Schema Common Sense Challenge Winograd Schema Common Sense Challenge Winograd Schemas (Levesque et al., 2011) I poured water from the bottle into the cup until it was full. I poured water from
More informationPerforming Under Pressure June 21 st, 1:00 EST
Performing Under Pressure June 21 st, 1:00 EST IHHP 2014 Survey data Business impact 83% of people agreed or strongly agreed that mismanaged pressure affects their managers' ability to lead people effectively
More informationCaptioning Your Video Using YouTube Online Accessibility Series
Captioning Your Video Using YouTube This document will show you how to use YouTube to add captions to a video, making it accessible to individuals who are deaf or hard of hearing. In order to post videos
More informationScientific Research. The Scientific Method. Scientific Explanation
Scientific Research The Scientific Method Make systematic observations. Develop a testable explanation. Submit the explanation to empirical test. If explanation fails the test, then Revise the explanation
More informationA Comparison of Deep Neural Network Training Methods for Large Vocabulary Speech Recognition
A Comparison of Deep Neural Network Training Methods for Large Vocabulary Speech Recognition LászlóTóth and Tamás Grósz MTA-SZTE Research Group on Artificial Intelligence Hungarian Academy of Sciences
More informationModel reconnaissance: discretization, naive Bayes and maximum-entropy. Sanne de Roever/ spdrnl
Model reconnaissance: discretization, naive Bayes and maximum-entropy Sanne de Roever/ spdrnl December, 2013 Description of the dataset There are two datasets: a training and a test dataset of respectively
More informationDiabetic Retinopathy Detection Using Eye Images
CS365:Artificial Intelligence Course Project Diabetic Retinopathy Detection Using Eye Images Mohit Singh Solanki 12419 mohitss@iitk.ac.in Supervisor: Dr. Amitabha Mukherjee April 18, 2015 Abstract Diabetic
More informationYour Task: Find a ZIP code in Seattle where the crime rate is worse than you would expect and better than you would expect.
Forensic Geography Lab: Regression Part 1 Payday Lending and Crime Seattle, Washington Background Regression analyses are in many ways the Gold Standard among analytic techniques for undergraduates (and
More informationQuantitative Analysis of the Elements of Interpersonal Trust of Poles
Quantitative Analysis of the Elements of Interpersonal Trust of Poles Alicja Grze kowiak Doi:10.5901/mjss.2014.v5n13p72 Wroc aw University of Economics Email: alicja.grzeskowiak@ue.wroc.pl Abstract Interpersonal
More informationAn Empirical Study of Adequate Vision Span for Attention-Based Neural Machine Translation
An Empirical Study of Adequate Vision Span for Attention-Based Neural Machine Translation Raphael Shu, Hideki Nakayama shu@nlab.ci.i.u-tokyo.ac.jp, nakayama@ci.i.u-tokyo.ac.jp The University of Tokyo In
More informationSearch e Fall /18/15
Sample Efficient Policy Click to edit Master title style Search Click to edit Emma Master Brunskill subtitle style 15-889e Fall 2015 11 Sample Efficient RL Objectives Probably Approximately Correct Minimizing
More informationRecurrent Neural Networks
CS 2750: Machine Learning Recurrent Neural Networks Prof. Adriana Kovashka University of Pittsburgh March 14, 2017 One Motivation: Descriptive Text for Images It was an arresting face, pointed of chin,
More informationIntroduction to Machine Learning. Katherine Heller Deep Learning Summer School 2018
Introduction to Machine Learning Katherine Heller Deep Learning Summer School 2018 Outline Kinds of machine learning Linear regression Regularization Bayesian methods Logistic Regression Why we do this
More informationNeural Network for Detecting Head Impacts from Kinematic Data. Michael Fanton, Nicholas Gaudio, Alissa Ling CS 229 Project Report
Neural Network for Detecting Head Impacts from Kinematic Data Michael Fanton, Nicholas Gaudio, Alissa Ling CS 229 Project Report 1. Abstract Mild Traumatic Brain Injury (mtbi) is a serious health concern,
More informationStacked Gender Prediction from Tweet Texts and Images
Stacked Gender Prediction from Tweet Texts and Images Notebook for PAN at CLEF 2018 Giovanni Ciccone, Arthur Sultan,, Léa Laporte, Előd Egyed-Zsigmond, Alaa Alhamzeh,, and Michael Granitzer * Université
More informationECG Signal Classification with Deep Learning Techniques
ECG Signal Classification with Deep Learning Techniques Chien You Huang, B04901147 Ruey Lin Jahn, B02901043 Sung-wei Huang, B04901093 Department of Electrical Engineering, National Taiwan University, Taipei,
More informationAutomated Prediction of Thyroid Disease using ANN
Automated Prediction of Thyroid Disease using ANN Vikram V Hegde 1, Deepamala N 2 P.G. Student, Department of Computer Science and Engineering, RV College of, Bangalore, Karnataka, India 1 Assistant Professor,
More informationarxiv: v1 [cs.cv] 21 Jul 2017
A Multi-Scale CNN and Curriculum Learning Strategy for Mammogram Classification William Lotter 1,2, Greg Sorensen 2, and David Cox 1,2 1 Harvard University, Cambridge MA, USA 2 DeepHealth Inc., Cambridge
More informationCPSC81 Final Paper: Facial Expression Recognition Using CNNs
CPSC81 Final Paper: Facial Expression Recognition Using CNNs Luis Ceballos Swarthmore College, 500 College Ave., Swarthmore, PA 19081 USA Sarah Wallace Swarthmore College, 500 College Ave., Swarthmore,
More informationThe Compact 3D Convolutional Neural Network for Medical Images
The Compact 3D Convolutional Neural Network for Medical Images Byung Bok Ahn Stanford University ntrant@stanford.edu Abstract In recent years, medical image processing has developed in the neural network
More informationA Deep Learning Approach to Identify Diabetes
, pp.44-49 http://dx.doi.org/10.14257/astl.2017.145.09 A Deep Learning Approach to Identify Diabetes Sushant Ramesh, Ronnie D. Caytiles* and N.Ch.S.N Iyengar** School of Computer Science and Engineering
More informationSynthesis of Gadolinium-enhanced MRI for Multiple Sclerosis patients using Generative Adversarial Network
Medical Application of GAN Synthesis of Gadolinium-enhanced MRI for Multiple Sclerosis patients using Generative Adversarial Network Sumana Basu School of Computer Science McGill University 260727568 sumana.basu@mail.mcgill.ca
More informationCh.20 Dynamic Cue Combination in Distributional Population Code Networks. Ka Yeon Kim Biopsychology
Ch.20 Dynamic Cue Combination in Distributional Population Code Networks Ka Yeon Kim Biopsychology Applying the coding scheme to dynamic cue combination (Experiment, Kording&Wolpert,2004) Dynamic sensorymotor
More informationOPTIMIZING CHANNEL SELECTION FOR SEIZURE DETECTION
OPTIMIZING CHANNEL SELECTION FOR SEIZURE DETECTION V. Shah, M. Golmohammadi, S. Ziyabari, E. Von Weltin, I. Obeid and J. Picone Neural Engineering Data Consortium, Temple University, Philadelphia, Pennsylvania,
More informationDeep Multimodal Fusion of Health Records and Notes for Multitask Clinical Event Prediction
Deep Multimodal Fusion of Health Records and Notes for Multitask Clinical Event Prediction Chirag Nagpal Auton Lab Carnegie Mellon Pittsburgh, PA 15213 chiragn@cs.cmu.edu Abstract The advent of Electronic
More informationCardiac Arrest Prediction to Prevent Code Blue Situation
Cardiac Arrest Prediction to Prevent Code Blue Situation Mrs. Vidya Zope 1, Anuj Chanchlani 2, Hitesh Vaswani 3, Shubham Gaikwad 4, Kamal Teckchandani 5 1Assistant Professor, Department of Computer Engineering,
More informationEfficient Deep Model Selection
Efficient Deep Model Selection Jose Alvarez Researcher Data61, CSIRO, Australia GTC, May 9 th 2017 www.josemalvarez.net conv1 conv2 conv3 conv4 conv5 conv6 conv7 conv8 softmax prediction???????? Num Classes
More informationAn Escalation Model of Consciousness
Bailey!1 Ben Bailey Current Issues in Cognitive Science Mark Feinstein 2015-12-18 An Escalation Model of Consciousness Introduction The idea of consciousness has plagued humanity since its inception. Humans
More informationReferring Expressions & Alternate Views of Summarization. Ling 573 Systems and Applications May 24, 2016
Referring Expressions & Alternate Views of Summarization Ling 573 Systems and Applications May 24, 2016 Content realization: Referring expressions Roadmap Alternate views of summarization: Dimensions of
More informationRising Scholars Academy 8 th Grade English I Summer Reading Project The Alchemist By Paulo Coelho
Rising Scholars Academy 8 th Grade English I Summer Reading Project The Alchemist By Paulo Coelho Welcome to 8th grade English I! Summer is a time where you can relax and have fun, but did you know you
More informationA RABBIT OMNIBUS (RABBIT, RUN; RABBIT REDUX; RABBIT IS RICH) BY JOHN UPDIKE
A RABBIT OMNIBUS (RABBIT, RUN; RABBIT REDUX; RABBIT IS RICH) BY JOHN UPDIKE DOWNLOAD EBOOK : A RABBIT OMNIBUS (RABBIT, RUN; RABBIT REDUX; Click link bellow and free register to download ebook: A RABBIT
More informationReframing Perspectives
Page 1 Reframing Perspectives Reframing is an essential part of the coaching process as it helps others to see things differently and, as a result, come to different, more empowering conclusions or feelings
More informationGLOOKO REPORT REFERENCE GUIDE
GLOOKO REPORT REFERENCE GUIDE November 2018 Version IFU-0010 02 Contents Intended Use... 2 Warnings... 2 Introduction... 3 Reports... 4 Report Criteria...4 Date Range... 4 Glucose Data Source... 4 Exercise
More informationVisual semantics: image elements. Symbols Objects People Poses
Visible Partisanship Polmeth XXXIII, Rice University, July 22, 2016 Convolutional Neural Networks for the Analysis of Political Images L. Jason Anastasopoulos ljanastas@uga.edu (University of Georgia,
More informationDeep Learning Analytics for Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations
Deep Learning Analytics for Predicting Prognosis of Acute Myeloid Leukemia with Cytogenetics, Age, and Mutations Andy Nguyen, M.D., M.S. Medical Director, Hematopathology, Hematology and Coagulation Laboratory,
More informationarxiv: v1 [cs.cv] 30 Aug 2018
Deep Chronnectome Learning via Full Bidirectional Long Short-Term Memory Networks for MCI Diagnosis arxiv:1808.10383v1 [cs.cv] 30 Aug 2018 Weizheng Yan 1,2,3, Han Zhang 3, Jing Sui 1,2, and Dinggang Shen
More informationCOMP9444 Neural Networks and Deep Learning 5. Convolutional Networks
COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks Textbook, Sections 6.2.2, 6.3, 7.9, 7.11-7.13, 9.1-9.5 COMP9444 17s2 Convolutional Networks 1 Outline Geometry of Hidden Unit Activations
More informationECG Beat Recognition using Principal Components Analysis and Artificial Neural Network
International Journal of Electronics Engineering, 3 (1), 2011, pp. 55 58 ECG Beat Recognition using Principal Components Analysis and Artificial Neural Network Amitabh Sharma 1, and Tanushree Sharma 2
More informationHierarchical Conflict Propagation: Sequence Learning in a Recurrent Deep Neural Network
Hierarchical Conflict Propagation: Sequence Learning in a Recurrent Deep Neural Network Andrew J.R. Simpson #1 # Centre for Vision, Speech and Signal Processing, University of Surrey Surrey, UK 1 Andrew.Simpson@Surrey.ac.uk
More information